Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1442 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1699. Min Range: -3.1699
Max Act: 3.1699. Min Act: -0.1700
Data Index: 3446128 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1699. Min Range: -3.1699
Max Act: 3.0911. Min Act: -0.1700
Data Index: 5823805 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1699. Min Range: -3.1699
Max Act: 3.0596. Min Act: -0.1700
Data Index: 8346336 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1699. Min Range: -3.1699
Max Act: 3.0280. Min Act: -0.1700
Data Index: 7381000 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1699. Min Range: -3.1699
Max Act: 2.9964. Min Act: -0.1700
Data Index: 5823804 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1699. Min Range: -3.1699
Max Act: 2.9173. Min Act: -0.1700
Data Index: 1107712 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1699. Min Range: -3.1699
Max Act: 2.9173. Min Act: -0.1700
Data Index: 1719240 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1699. Min Range: -3.1699
Max Act: 2.9014. Min Act: -0.1700
Data Index: 1274651 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1699. Min Range: -3.1699
Max Act: 2.8697. Min Act: -0.1700
Data Index: 6573576 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1699. Min Range: -3.1699
Max Act: 2.8697. Min Act: -0.1700
Data Index: 3101873 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1699. Min Range: -3.1699
Max Act: 2.8538. Min Act: -0.1700
Data Index: 8354617 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1699. Min Range: -3.1699
Max Act: 2.8697. Min Act: -0.1700
Data Index: 4237686 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1699. Min Range: -3.1699
Max Act: 2.8220. Min Act: -0.1700
Data Index: 2579225 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1699. Min Range: -3.1699
Max Act: 2.8379. Min Act: -0.1700
Data Index: 958779 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1699. Min Range: -3.1699
Max Act: 2.8379. Min Act: -0.1700
Data Index: 5528514 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1699. Min Range: -3.1699
Max Act: 2.8220. Min Act: -0.1700
Data Index: 1799144 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1699. Min Range: -3.1699
Max Act: 2.8379. Min Act: -0.1700
Data Index: 5530830 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1699. Min Range: -3.1699
Max Act: 2.8061. Min Act: -0.1700
Data Index: 6900803 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1699. Min Range: -3.1699
Max Act: 2.8061. Min Act: -0.1700
Data Index: 7294705 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1699. Min Range: -3.1699
Max Act: 2.8061. Min Act: -0.1700
Data Index: 5319684 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #19